Home / Current Issue / Paper 1722768
AI-Assisted Cardiotocography Interpretation for Early Detection of Fetal Distress: Implications for Obstetric Care in Saudi Arabia
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence
DOI: https://doi.org/10.64388/IREV10I3-1722768
Abstract
Cardiotocography (CTG) remains one of the most frequently used methods for assessing fetal wellbeing during labor, particularly in pregnancies requiring continuous intrapartum surveillance. Despite its widespread use, conventional visual CTG interpretation is limited by interobserver and interobserver variability, inconsistent application of clinical guidelines, signal artefacts, and the relatively low positive predictive value of abnormal patterns for actual fetal hypoxia. Artificial intelligence (AI), machine learning (ML), and deep-learning techniques are increasingly being investigated as tools for improving the consistency and predictive value of CTG interpretation. This review evaluates contemporary evidence on AI-assisted CTG analysis for the early recognition of fetal compromise and examines its potential application within Saudi Arabian maternity services. A structured literature review was undertaken using evidence published primarily between 2020 and 2025. Current research demonstrates that machine-learning and deep-learning models can identify CTG abnormalities, predict fetal acidemia, and provide near-real-time assessment of fetal-heart-rate responses. Multicenter deep-learning studies have demonstrated promising discrimination for severe neonatal acidemia, while AI-based models may reduce subjectivity by continuously evaluating fetal-heart-rate and uterine-contraction patterns. However, clinical implementation remains limited by inconsistent outcome definitions, retrospective datasets, signal-quality problems, inadequate external validation, algorithmic bias, class imbalance, and limited explainability. AI should therefore augment rather than replace obstetric judgment. For Saudi Arabia, integrating AI-assisted CTG with electronic maternal records, central fetal-monitoring platforms, and structured escalation protocols could support high-volume maternity hospitals and align with the digital-health objectives of Saudi Vision 2030. A clinician-led human-AI model is proposed to strengthen fetal surveillance while maintaining patient safety, transparency, and professional accountability.
Keywords
Cardiotocography; Artificial Intelligence; Fetal Hypoxia; Fetal Distress; Fetal Monitoring; Machine Learning; Deep Learning; Clinical Decision Support; Saudi Arabia; Vision 2030.
How to cite this paper
@article{1722768,
author = {Amina Majid},
title = {AI-Assisted Cardiotocography Interpretation for Early Detection of Fetal Distress: Implications for Obstetric Care in Saudi Arabia},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {3},
pages = {575-586},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1722768.pdf},
abstract = {Cardiotocography (CTG) remains one of the most frequently used methods for assessing fetal wellbeing during labor, particularly in pregnancies requiring continuous intrapartum surveillance. Despite its widespread use, conventional visual CTG interpretation is limited by interobserver and interobserver variability, inconsistent application of clinical guidelines, signal artefacts, and the relatively low positive predictive value of abnormal patterns for actual fetal hypoxia. Artificial intelligence (AI), machine learning (ML), and deep-learning techniques are increasingly being investigated as tools for improving the consistency and predictive value of CTG interpretation. This review evaluates contemporary evidence on AI-assisted CTG analysis for the early recognition of fetal compromise and examines its potential application within Saudi Arabian maternity services. A structured literature review was undertaken using evidence published primarily between 2020 and 2025. Current research demonstrates that machine-learning and deep-learning models can identify CTG abnormalities, predict fetal acidemia, and provide near-real-time assessment of fetal-heart-rate responses. Multicenter deep-learning studies have demonstrated promising discrimination for severe neonatal acidemia, while AI-based models may reduce subjectivity by continuously evaluating fetal-heart-rate and uterine-contraction patterns. However, clinical implementation remains limited by inconsistent outcome definitions, retrospective datasets, signal-quality problems, inadequate external validation, algorithmic bias, class imbalance, and limited explainability. AI should therefore augment rather than replace obstetric judgment. For Saudi Arabia, integrating AI-assisted CTG with electronic maternal records, central fetal-monitoring platforms, and structured escalation protocols could support high-volume maternity hospitals and align with the digital-health objectives of Saudi Vision 2030. A clinician-led human-AI model is proposed to strengthen fetal surveillance while maintaining patient safety, transparency, and professional accountability.},
keywords = {Cardiotocography; Artificial Intelligence; Fetal Hypoxia; Fetal Distress; Fetal Monitoring; Machine Learning; Deep Learning; Clinical Decision Support; Saudi Arabia; Vision 2030.},
month = {September},
doi = {https://doi.org/10.64388/IREV10I3-1722768}
}